EEG/EMG Signal Decoding for the NeurIPS 2026 Foundation Challenge
Dr. Ramana Kumar Vinjamuri, Department of Computer Science and Electrical Engineering.
Sruthi Sundharram, Department of Computer Science and Electrical Engineering.
This project focuses on developing and evaluating machine learning models for decoding electroencephalography (EEG) and electromyography (EMG) biosignals as part of the EEG/EMG Foundation Challenge at the NeurIPS 2026 Brain & Body Workshop. The work involves processing biosignal datasets, training and evaluating decoding models, and assessing model generalization across different stimuli, recording sessions, and individuals.
Access to UMBC’s High Performance Computing (HPC) cluster, Chip, is requested to support computationally intensive data preprocessing, model training, hyperparameter tuning, and experimental evaluation. HPC resources will enable efficient execution of experiments on the challenge datasets and support the development of reproducible models for biosignal decoding and generalization.
Brain Computer Interfaces and Human-Robot Interaction
Dr. Ramana Kumar Vinjamuri, Department of Computer Science and Electrical Engineering 2024
The human central nervous system (CNS) effortlessly performs complex hand movements with the control and coordination of multiple degrees of freedom. It is hypothesized that the CNS might use kinematic synergies to reduce the complexity of movements, but how these kinematic synergies are encoded in the CNS remains unclear. In order to investigate the neural representations of kinematic synergies, scalp electroencephalographic (EEG) signals and hand kinematics are recorded during representative types of hand grasping. These multimodal signals are analyzed using high performance computing. The results have promising applications in noninvasive neural control of synergy-based prostheses and exoskeletons and human robot interaction. Emotionally intelligent interactions between humans and robots are essential to accomplish shared tasks in collaborative processes. Robots may exploit various communication channels to recognize human emotions, including hearing, speech, sight, touch, and learning. They can then use this information to adapt their behavior in a way that is socially appropriate for humans. In this research, we focus on neurophysiological and behavioral signals of communication.